© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90054
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or resignation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hlen
    -0.08
    frau
    -0.07
    omatic
    -0.07
    ÑĮко
    -0.07
    steen
    -0.07
     Kaynak
    -0.07
    .gb
    -0.07
    ÑĤÑİ
    -0.07
    preload
    -0.07
    svp
    -0.06
    POSITIVE LOGITS
    chia
    0.07
    umin
    0.06
    typ
    0.06
    ether
    0.06
    ather
    0.06
     typical
    0.06
    çİĽ
    0.06
    ki
    0.06
    chers
    0.06
     vet
    0.05
    Activations Density 0.006%

    No Known Activations